activity
20242026
collaborators

8 papers

cs.AI2026

Fluid Reasoning Representations

Dmitrii Kharlapenko, Alessandro Stolfo, Terry Jingchen Zhang +4

Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking. Yet we lack a mechanistic account of how extended t…

cs.AI2026

On the Emergence of Induction Heads for In-Context Learning

Tiberiu Musat, Tiago Pimentel, Lorenzo Noci +3

Transformers have become the dominant architecture for natural language processing. Part of their success is owed to a remarkable capability known as in-context learning (ICL): the…

cs.LG2025

Dense SAE Latents Are Features, Not Bugs

Xiaoqing Sun, Alessandro Stolfo, Joshua Engels +4

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that…

cs.CL2025

Transferring Linear Features Across Language Models With Model Stitching

Alan Chen, Jack Merullo, Alessandro Stolfo +1

In this work, we demonstrate that affine mappings between residual streams of language models is a cheap way to effectively transfer represented features between models. We apply t…

cs.CL2025

Probing for Arithmetic Errors in Language Models

Yucheng Sun, Alessandro Stolfo, Mrinmaya Sachan

We investigate whether internal activations in language models can be used to detect arithmetic errors. Starting with a controlled setting of 3-digit addition, we show that simple…

cs.LG2025

MIB: A Mechanistic Interpretability Benchmark

Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20

How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…